Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Data size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .magic
    -0.07
    "data
    -0.07
    izza
    -0.06
    )frame
    -0.06
    psz
    -0.06
     blk
    -0.06
    Lic
    -0.06
     vpn
    -0.06
     Paz
    -0.06
    entic
    -0.06
    POSITIVE LOGITS
     PR
    0.07
     recieved
    0.06
     такого
    0.06
     =[
    0.06
    (effect
    0.06
    IBOutlet
    0.06
    表示
    0.06
    ี↵
    0.06
    cbd
    0.06
     uber
    0.06
    Act Density 0.001%

    No Known Activations